DocumentCode :
58825
Title :
Gender-Driven Emotion Recognition Through Speech Signals For Ambient Intelligence Applications
Author :
Bisio, Igor ; Delfino, Alessandro ; Lavagetto, Fabio ; Marchese, Mario ; Sciarrone, Andrea
Author_Institution :
Dept. of Electr., Electron., Telecommun. Eng. & Naval Archit., Univ. of Genoa, Genoa, Italy
Volume :
1
Issue :
2
fYear :
2013
fDate :
Dec. 2013
Firstpage :
244
Lastpage :
257
Abstract :
This paper proposes a system that allows recognizing a person´s emotional state starting from audio signal registrations. The provided solution is aimed at improving the interaction among humans and computers, thus allowing effective human-computer intelligent interaction. The system is able to recognize six emotions(anger, boredom, disgust, fear, happiness, and sadness) and the neutral state. This set of emotional states is widely used for emotion recognition purposes. It also distinguishes a single emotion versus all the other possible ones, as proven in the proposed numerical results. The system is composed of two subsystems: 1) gender recognition(GR) and 2) emotion recognition(ER). The experimental analysis shows the performance in terms of accuracy of the proposed ER system. The results highlight that the a priori knowledge of the speaker´s gender allows a performance increase. The obtained results show also that the features selection adoption assures a satisfying recognition rate and allows reducing the employed features. Future developments of the proposed solution may include the implementation of this system over mobile devices such as smartphones.
Keywords :
audio signal processing; emotion recognition; feature selection; human computer interaction; speaker recognition; support vector machines; ER system; GR; a priori knowledge; ambient intelligence applications; anger; audio signal registrations; boredom; disgust; fear; features selection adoption; gender-driven emotion recognition; happiness; human-computer intelligent interaction; mobile devices; neutral state; person emotional state recognition; recognition rate; sadness; smartphones; speaker gender; speech signals; support vector machine; Databases; Emotion recognition; Feature extraction; Gender issues; Speech recognition; Support vector machines; Human-computer intelligent interaction; emotion recognition; gender recognition; pitch estimation; support vector machine;
fLanguage :
English
Journal_Title :
Emerging Topics in Computing, IEEE Transactions on
Publisher :
ieee
ISSN :
2168-6750
Type :
jour
DOI :
10.1109/TETC.2013.2274797
Filename :
6568890
Link To Document :
بازگشت